54 lines
1.2 KiB
YAML
54 lines
1.2 KiB
YAML
# FASTVIDEO_ATTENTION_BACKEND=ATTN_QAT_INFER FASTVIDEO_VSA_PTX_BLACKWELL=0 FASTVIDEO_FA4=0 \
|
|
# FLASHINFER_CUDA_ARCH_LIST=12.0a \
|
|
# fastvideo serve --config examples/serving/openai_compacth3_rtx_pro6000.yaml
|
|
generator:
|
|
model_path: ./CompactH3
|
|
engine:
|
|
num_gpus: 1
|
|
use_fsdp_inference: false
|
|
quantization:
|
|
transformer_quant: NVFP4
|
|
layer_profile: h3_dit
|
|
parallelism:
|
|
tp_size: 1
|
|
sp_size: 1
|
|
offload:
|
|
dit: false
|
|
dit_layerwise: false
|
|
text_encoder: false
|
|
image_encoder: true
|
|
vae: false
|
|
pin_cpu_memory: true
|
|
lazy_module_load: false
|
|
compile:
|
|
enabled: false
|
|
vae_enabled: true
|
|
pipeline:
|
|
workload_type: t2v
|
|
experimental:
|
|
attention_backend: ATTN_QAT_INFER
|
|
h3_sequential_load: false
|
|
inference_torch_compile: false
|
|
vae_parallel_decode: false
|
|
video_decode_backend: h3-vae
|
|
|
|
server:
|
|
host: 127.0.0.1
|
|
port: 8000
|
|
output_dir: outputs/openai_compacth3_rtx_pro6000
|
|
served_model_name: compacth3
|
|
|
|
default_request:
|
|
negative_prompt: ""
|
|
sampling:
|
|
height: 768
|
|
width: 1344
|
|
num_frames: 124
|
|
fps: 24
|
|
num_inference_steps: 5
|
|
guidance_scale: 1.0
|
|
batch_cfg: false
|
|
seed: 2026
|
|
output:
|
|
return_frames: false
|